Rebuttal

Skill dengzhe-hou/best-skills-research-writing/skills/review/rebuttal

Curated skills from 50k+ star repos for research, writing, and review, ranked candidates per scenario

Install

npx -y skills add dengzhe-hou/best-skills-research-writing --skill rebuttal

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits.

SKILL.md

2.8 KB, as published. Nobody here has run it

Rebuttal Pipeline

Based on: wanshuiyin/Auto-claude-code-research-in-sleep Original License: MIT

Overview

This skill prepares a grounded, venue-compliant rebuttal for external reviews.

Safety Model

Three hard gates — if any fails, do NOT finalize:

Provenance gate — every factual statement maps to: paper, review, user_confirmed_result, or future_work. No source = blocked.
Commitment gate — every promise maps to: already_done, approved_for_rebuttal, or future_work_only. Not approved = blocked.
Coverage gate — every reviewer concern ends in: answered, deferred_intentionally, or needs_user_input. No issue disappears.

Workflow

Phase 0: Resume or Initialize

Load paper, reviews, venue rules, any user-confirmed evidence.

Phase 1: Validate Inputs and Normalize Reviews

Normalize all reviewer text into raw format.

Phase 2: Atomize and Classify Reviewer Concerns

Create issue board with:

issue_id (e.g., R1-C2)
reviewer, round, raw_anchor
issue_type: assumptions / theorem_rigor / novelty / empirical_support / clarity / other
severity: critical / major / minor
response_mode: direct_clarification / grounded_evidence / narrow_concession / etc.

Phase 3: Build Strategy Plan

Identify 2-4 global themes
Choose response mode per issue
Build character budget
Identify blocked claims

Phase 4: Draft Initial Rebuttal

Structure:

Short opener — thank reviewers + global resolutions
Per-reviewer numbered responses — answer → evidence → implication
Short closing — resolved / remaining / acceptance case

Phase 5: Safety Validation

Run all lints:

Coverage — every issue maps to draft anchor
Provenance — every factual sentence has source
Commitment — promises are approved
Tone — flag aggressive/submissive phrases
Limit — exact character count

Phase 6: Stress Test

External reviewer checks for:

Unanswered or weakly answered concerns
Unsupported factual statements
Risky or unapproved promises
Tone problems

Phase 7: Finalize

Output:

PASTE_READY.txt — strict version, exact character count
REBUTTAL_DRAFT_rich.md — extended version with more detail

Key Rules

Never fabricate. No invented evidence, numbers, derivations, citations.
Never overpromise. Only promise what user explicitly approved.
Full coverage. Every reviewer concern tracked and accounted for.
Evidence > rhetoric. Derivations and numbers over prose.
Concede selectively. Narrow honest concessions > broad denials.
Respect the limit. Character budget is a hard constraint.